Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Jiaya JiaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works60 from public data
- 1,838
- Structure extraction from texture via relative total variation948
This work proposes new inherent variation and relative total variation measures, which capture the essential difference of these two types of visual forms, and develops an efficient optimization system to extract main structures.
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels664
The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure and unify the three tasks into one model, termed the OneAlign.
- 617
- Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching502
A novel cascade CNN architecture composing of two stages that advances the recently proposed DispNet by equipping it with extra up-convolution modules, leading to disparity images with more details, and shows that residual learning provides more effective refinement.
- Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives463
The Disentangled Objective Video Quality Evaluator (DOVER) is proposed, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective, and the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective.
- TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment423
This work proposes a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as TOPIQ, and designs a heuristic coarse-to-fine network that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner.
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision309
Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment, confirms that MLLMs possess preliminary low-level visual skills.
- Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning306
A new SSL framework, named Guided Collaborative Training (GCT), is presented, with two main technical contributions, that addresses the issues caused by the dense outputs through a novel flaw detector and can be applied to a wide range of pixel-wise tasks without structural adaptation.
- Accurate Single Stage Detector Using Recurrent Rolling Convolution297
A novel single stage end-to-end trainable object detection network is proposed by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are deep in context.
- BeautyGAN283
A dual input/output Generative Adversarial Network that enables the network to learn translation on instance-level through unsupervised adversarial learning, and could generate visually pleasant makeup faces and accurate transferring results.
- Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning276
This work shows that the coupled EMA teacher causes a performance bottleneck and introduces Dual Student, which replaces the teacher with another student, and defines a novel concept, stable sample, following which a stabilization constraint is designed for the structure to be trainable.
- MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition244
A light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image that outperforms prior trimap-free methods by a large margin and achieves remarkable results on daily photos and videos.
- 239
- Deep Edge-Aware Filters205
This work makes the attempt to learn a big and important family of edge-aware operators from data based on a deep convolutional neural network with a gradient domain training procedure, which gives rise to a powerful tool to approximate various filters without knowing the original models and implementation details.
- NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image204
A new, larger-than-ever, natural hyperspectral image data set is presented, containing a total of 510 HS images, and the proposed methods gauge the state-of-the-art in spectral reconstruction from an RGB image.
- Hierarchical Regression Network for Spectral Reconstruction from RGB Images200
A 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction with a residual dense block to remove artifacts of real world RGB images and a residual global block to build attention mechanism for enlarging perceptive field is proposed.
- Shepard convolutional neural networks190
This paper draws on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network and shows that by adding only a few feature maps in the new Shepard layers, the network is able to achieve stronger results than a much deeper architecture.
- Polarized Reflection Removal With Perfect Alignment in the Wild152
This work identifies the misalignment issues of existing reflection removal datasets where the collected reflection-free images are not perfectly aligned with input mixed images due to glass refraction and proposes a polarized reflection removal model with a two-stage architecture.
- 129
- Towards Open-ended Visual Quality Comparison121
This work demonstrates that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench.
- Look, Listen and Learn — A Multimodal LSTM for Speaker Identification115
A novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input is described which outperforms the state-of-the-art systems in speaker identification with lower false alarm rate and higher recognition accuracy.
- NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results106
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results, based on the SIDD benchmark.
- AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results101
The AIM 2020 challenge on efficient single image super-resolution was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images with focus on the proposed solutions and results.
- Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment99
This work proposes a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS), and the resultant samples are named fragments, a network architecture tailored specifically for fragments that achieves up to 1612× efficiency than the existing state-of-the-art VQA benchmarks.
- DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment86
The proposed Temporal Distortion-Content Transformers for Video Quality Assessment (DisCoVQA) reaches state-of-the-art performance on several VQA benchmarks without any extra pre-training datasets and up to 10% better generalization ability than existing methods.
- 84
- Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach80
The MaxVQA is proposed, a language-prompted VQA approach that modifies vision-language foundation model CLIP to better capture important quality issues as observed in the authors' analyses.
- A sparse control model for image and video editing80
This work discovers inherent limitation of existing methods for their implicit requirement on where and how the strokes are drawn, and presents a new system that is principled on minimizing the amount of work put in user interaction.
- Deep Surface Normal Estimation With Hierarchical RGB-D Fusion79
A hierarchical fusion network with adaptive feature re-weighting is proposed for surface normal estimation from a single RGB-D image, outperforming state-of-the-art normal estimation schemes.
- Is a Green Screen Really Necessary for Real-Time Portrait Matting?70
A light-weight matting objective decomposition network (MODNet) is presented, which can process portrait matting from a single input image in real time and greatly outperforms prior trimap-free methods.
- Dual-Camera Super-Resolution with Aligned Attention Modules68
This work proposes a self-supervised domain adaptation strategy for real-world images that generalizes the standard patch-based feature matching with spatial alignment operations and further explores the dual-camera super-resolution that is one promising application of RefSR.
- 59
- 56
- 44
- Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment41
Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.
- 29
- 26
- A Categorized Reflection Removal Dataset with Diverse Real-world Scenes21
It is shown that state-of-the-art reflection removal methods generally perform well on blurry reflection but fail in obtaining satisfying performance on other types of real-world reflection.
- Dense scattering layer removal21
This work proposes a new model, together with advanced optimization, to separate a thick scattering media layer from a single natural image, and introduces non-local structure-aware regularization to properly constrain transmission estimation without introducing the halo artifacts.
- 20
- Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment19
An efficient fine-tuning scheme is devised for BVQI-Local that jointly optimizes text prompts and final fusion weights, resulting in state-of-the-art performance and superior generalization ability in comparison to prevalent opinion-driven VQA methods.
- 18
- ChildPredictor: A Child Face Prediction Framework With Disentangled Learning15
A new disentangled learning strategy for children's face prediction called ChildPredictor, which transfers human faces to genetic factors by encoders and back by generators, and learns the relationship between the genetic factors of parents and children through a mapping function.
- DSR: Direct Self-Rectification for Uncalibrated Dual-Lens Cameras15
This paper proposes a cost-effective solution to perform stereo rectification for dual-lens cameras called direct self-rectification, short for DSR, which removes the need of individual offline calibration for every pair of dual- lens cameras.
- 13
- Is a Green Screen Really Necessary for Real-Time Human Matting?11
A light-weight matting objective decomposition network (MODNet), which can process human matting from a single input image in real time and greatly outperforms prior trimap-free methods.
- Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment10
This paper demonstrates that with proper injection of local distortion features, a larger pretrained and fixed foundation model performs better in IQA tasks, indicating that IQA is not only a low-level problem but also benefits from stronger high-level features drawn from large-scale pretrained models.
- 10
- 9
- 9
- Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring7
A hierarchical convolutional neural network called QRNet is designed to recover high-quality RGB images and demonstrates superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets.
- 7
- 4
- Enhancing HDR Imaging with Joint Denoising and Deblurring3
A novel and efficient attention-based multi-exposure HDR imaging method, which skillfully selects the optimal information from corrupted LDR inputs by the authors' customized cross-attention mechanism to generate HDR information is proposed.
- 3
- 2
- 2
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.